
import pandas as pd


food = pd.read_csv(r'D:\Data analytics\Projects\Pandas\u_food_marketing.csv')
food.head()


food


pd.set_option('display.max.row',2300)
pd.set_option('display.max.columns', 40)


food


food[food.duplicated()].sum()

Income                  9366769.0
Kidhome                      79.0
Teenhome                     87.0
Recency                    9277.0
MntWines                  55672.0
MntFruits                  4936.0
MntMeatProducts           28906.0
MntFishProducts            7256.0
MntSweetProducts           4708.0
MntGoldProds               8380.0
NumDealsPurchases           403.0
NumWebPurchases             725.0
NumCatalogPurchases         488.0
NumStorePurchases          1104.0
NumWebVisitsMonth           975.0
AcceptedCmp3                 12.0
AcceptedCmp4                  9.0
AcceptedCmp5                 15.0
AcceptedCmp1                  9.0
AcceptedCmp2                  4.0
Complain                      1.0
Z_CostContact               552.0
Z_Revenue                  2024.0
Response                     22.0
Age                        9358.0
Customer_Days            464574.0
marital_Divorced             16.0
marital_Married              69.0
marital_Single               34.0
marital_Together             59.0
marital_Widow                 6.0
education_2n Cycle           15.0
education_Basic               5.0
education_Graduation         98.0
education_Master             29.0
education_PhD                37.0
MntTotal                 101478.0
MntRegularProds           93098.0
AcceptedCmpOverall           49.0
dtype: float64


food.drop_duplicates(keep=False, inplace=True)


food


food.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1843 entries, 0 to 2204
Data columns (total 39 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   Income                1843 non-null   float64
 1   Kidhome               1843 non-null   int64  
 2   Teenhome              1843 non-null   int64  
 3   Recency               1843 non-null   int64  
 4   MntWines              1843 non-null   int64  
 5   MntFruits             1843 non-null   int64  
 6   MntMeatProducts       1843 non-null   int64  
 7   MntFishProducts       1843 non-null   int64  
 8   MntSweetProducts      1843 non-null   int64  
 9   MntGoldProds          1843 non-null   int64  
 10  NumDealsPurchases     1843 non-null   int64  
 11  NumWebPurchases       1843 non-null   int64  
 12  NumCatalogPurchases   1843 non-null   int64  
 13  NumStorePurchases     1843 non-null   int64  
 14  NumWebVisitsMonth     1843 non-null   int64  
 15  AcceptedCmp3          1843 non-null   int64  
 16  AcceptedCmp4          1843 non-null   int64  
 17  AcceptedCmp5          1843 non-null   int64  
 18  AcceptedCmp1          1843 non-null   int64  
 19  AcceptedCmp2          1843 non-null   int64  
 20  Complain              1843 non-null   int64  
 21  Z_CostContact         1843 non-null   int64  
 22  Z_Revenue             1843 non-null   int64  
 23  Response              1843 non-null   int64  
 24  Age                   1843 non-null   int64  
 25  Customer_Days         1843 non-null   int64  
 26  marital_Divorced      1843 non-null   int64  
 27  marital_Married       1843 non-null   int64  
 28  marital_Single        1843 non-null   int64  
 29  marital_Together      1843 non-null   int64  
 30  marital_Widow         1843 non-null   int64  
 31  education_2n Cycle    1843 non-null   int64  
 32  education_Basic       1843 non-null   int64  
 33  education_Graduation  1843 non-null   int64  
 34  education_Master      1843 non-null   int64  
 35  education_PhD         1843 non-null   int64  
 36  MntTotal              1843 non-null   int64  
 37  MntRegularProds       1843 non-null   int64  
 38  AcceptedCmpOverall    1843 non-null   int64  
dtypes: float64(1), int64(38)
memory usage: 575.9 KB


food['Total_Children'] = food[['Kidhome', 'Teenhome']].sum(axis=1)


food.head()


food['marital_Divorced'] = food['marital_Divorced'].replace({1:5,0:0})


food[food['marital_Divorced'] != 0].head()


food['marital_Married'] = food['marital_Married'].replace({1:4,0:0})
food['marital_Single'] = food['marital_Single'].replace({1:3,0:0})
food['marital_Together'] = food['marital_Together'].replace({1:2,0:0})
food['marital_Widow'] = food['marital_Widow'].replace({1:1,0:0})


food['Marital_Status'] = food[['marital_Divorced', 'marital_Married', 'marital_Single', 'marital_Together', 'marital_Widow']].sum(axis=1)


food[food['Marital_Status'] != 0].head()


food['Marital_Status_str'] = food['Marital_Status'].map({5:'Divorced', 4:'Married', 3:'Single', 2:'Together', 1:'Widow'})


food[food['Marital_Status_str'] != 0].head()


food.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1843 entries, 0 to 2204
Data columns (total 42 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   Income                1843 non-null   float64
 1   Kidhome               1843 non-null   int64  
 2   Teenhome              1843 non-null   int64  
 3   Recency               1843 non-null   int64  
 4   MntWines              1843 non-null   int64  
 5   MntFruits             1843 non-null   int64  
 6   MntMeatProducts       1843 non-null   int64  
 7   MntFishProducts       1843 non-null   int64  
 8   MntSweetProducts      1843 non-null   int64  
 9   MntGoldProds          1843 non-null   int64  
 10  NumDealsPurchases     1843 non-null   int64  
 11  NumWebPurchases       1843 non-null   int64  
 12  NumCatalogPurchases   1843 non-null   int64  
 13  NumStorePurchases     1843 non-null   int64  
 14  NumWebVisitsMonth     1843 non-null   int64  
 15  AcceptedCmp3          1843 non-null   int64  
 16  AcceptedCmp4          1843 non-null   int64  
 17  AcceptedCmp5          1843 non-null   int64  
 18  AcceptedCmp1          1843 non-null   int64  
 19  AcceptedCmp2          1843 non-null   int64  
 20  Complain              1843 non-null   int64  
 21  Z_CostContact         1843 non-null   int64  
 22  Z_Revenue             1843 non-null   int64  
 23  Response              1843 non-null   int64  
 24  Age                   1843 non-null   int64  
 25  Customer_Days         1843 non-null   int64  
 26  marital_Divorced      1843 non-null   int64  
 27  marital_Married       1843 non-null   int64  
 28  marital_Single        1843 non-null   int64  
 29  marital_Together      1843 non-null   int64  
 30  marital_Widow         1843 non-null   int64  
 31  education_2n Cycle    1843 non-null   int64  
 32  education_Basic       1843 non-null   int64  
 33  education_Graduation  1843 non-null   int64  
 34  education_Master      1843 non-null   int64  
 35  education_PhD         1843 non-null   int64  
 36  MntTotal              1843 non-null   int64  
 37  MntRegularProds       1843 non-null   int64  
 38  AcceptedCmpOverall    1843 non-null   int64  
 39  Total_Children        1843 non-null   int64  
 40  Marital_Status        1843 non-null   int64  
 41  Marital_Status_str    1843 non-null   object 
dtypes: float64(1), int64(40), object(1)
memory usage: 619.1+ KB


food['education_2n Cycle'] = food['education_2n Cycle'].replace({1:1,0:0})
food['education_Basic'] = food['education_Basic'].replace({1:2,0:0})
food['education_Graduation'] = food['education_Graduation'].replace({1:3,0:0})
food['education_Master'] = food['education_Master'].replace({1:4,0:0})
food['education_PhD'] = food['education_PhD'].replace({1:5,0:0})


food['Education_Status'] = food[['education_2n Cycle', 'education_Basic', 'education_Graduation', 'education_Master', 'education_PhD']].sum(axis=1)


food[food['Education_Status'] != 0].head()


food['Accepted_Campaigns'] = food[['AcceptedCmp3', 'AcceptedCmp4', 'AcceptedCmp5', 'AcceptedCmp1', 'AcceptedCmp2', 'Response']].sum(axis=1)


food['Accepted_Campaigns'] = (food['Accepted_Campaigns'] != 0).astype(int)


food[food['Accepted_Campaigns'] != 0].head()


food.corr(method='pearson')['Accepted_Campaigns'].sort_values(ascending=False)

Accepted_Campaigns      1.000000
AcceptedCmpOverall      0.713352
Response                0.685109
AcceptedCmp4            0.465985
AcceptedCmp3            0.453742
AcceptedCmp5            0.441264
AcceptedCmp1            0.426687
MntWines                0.416651
MntTotal                0.393910
MntRegularProds         0.391931
NumCatalogPurchases     0.322143
MntMeatProducts         0.298240
Income                  0.292812
NumWebPurchases         0.221217
MntGoldProds            0.188209
AcceptedCmp2            0.174619
MntSweetProducts        0.156430
MntFruits               0.149973
MntFishProducts         0.145404
NumStorePurchases       0.144965
Customer_Days           0.083874
Education_Status        0.062534
marital_Single          0.051947
education_PhD           0.043488
marital_Widow           0.038379
Age                     0.013540
education_Master        0.012535
marital_Divorced        0.002049
education_Graduation   -0.006359
Marital_Status         -0.021551
marital_Together       -0.022349
Complain               -0.025798
education_2n Cycle     -0.036272
NumDealsPurchases      -0.039332
marital_Married        -0.040256
NumWebVisitsMonth      -0.056732
education_Basic        -0.059021
Recency                -0.107196
Teenhome               -0.125445
Kidhome                -0.187111
Total_Children         -0.227585
Z_CostContact                NaN
Z_Revenue                    NaN
Name: Accepted_Campaigns, dtype: float64


import seaborn as sns
sns.heatmap(food.corr(method = 'pearson'))

<AxesSubplot:>


all_correlations = food.corr(method = 'pearson')
all_correlations = all_correlations[(all_correlations > 0.3) & (all_correlations < 1)]

sns.heatmap(all_correlations)

<AxesSubplot:>


all_correlations['Accepted_Campaigns']

Income                       NaN
Kidhome                      NaN
Teenhome                     NaN
Recency                      NaN
MntWines                0.416651
MntFruits                    NaN
MntMeatProducts              NaN
MntFishProducts              NaN
MntSweetProducts             NaN
MntGoldProds                 NaN
NumDealsPurchases            NaN
NumWebPurchases              NaN
NumCatalogPurchases     0.322143
NumStorePurchases            NaN
NumWebVisitsMonth            NaN
AcceptedCmp3            0.453742
AcceptedCmp4            0.465985
AcceptedCmp5            0.441264
AcceptedCmp1            0.426687
AcceptedCmp2                 NaN
Complain                     NaN
Z_CostContact                NaN
Z_Revenue                    NaN
Response                0.685109
Age                          NaN
Customer_Days                NaN
marital_Divorced             NaN
marital_Married              NaN
marital_Single               NaN
marital_Together             NaN
marital_Widow                NaN
education_2n Cycle           NaN
education_Basic              NaN
education_Graduation         NaN
education_Master             NaN
education_PhD                NaN
MntTotal                0.393910
MntRegularProds         0.391931
AcceptedCmpOverall      0.713352
Total_Children               NaN
Marital_Status               NaN
Education_Status             NaN
Accepted_Campaigns           NaN
Name: Accepted_Campaigns, dtype: float64


food


food['Age'].sort_values()

43      24
1150    24
2180    25
727     25
1824    25
894     26
400     26
1143    26
1330    27
2061    27
901     27
811     28
1787    28
2131    28
1688    28
295     28
129     28
2054    28
1226    28
1340    28
1046    28
891     28
1696    29
1961    29
1649    29
826     29
1022    29
873     29
102     29
505     29
1159    29
709     29
1547    29
2014    29
104     29
528     30
1152    30
1582    30
1821    30
1187    30
229     30
2167    30
1587    30
1668    30
1469    30
2134    30
1932    30
1389    30
500     30
485     30
1865    31
179     31
534     31
1293    31
1511    31
1515    31
668     31
718     31
1121    31
26      31
414     31
411     31
410     31
1676    31
913     31
911     31
973     31
839     31
843     31
683     32
1823    32
457     32
1537    32
1510    32
133     32
1509    32
207     32
1467    32
53      32
193     32
156     32
180     32
1567    32
289     32
282     32
169     32
742     32
952     32
1039    33
1503    33
381     33
504     33
507     33
1007    33
747     33
1453    33
983     33
1876    33
1849    33
1331    33
981     33
396     33
1804    33
842     33
1665    33
78      33
1559    33
1592    33
648     33
1521    33
925     33
13      33
1564    33
889     34
1077    34
508     34
1200    34
264     34
422     34
1962    34
794     34
924     34
1082    34
847     34
2095    34
324     34
1129    34
216     34
1985    34
1211    34
588     34
1207    34
690     34
409     34
1024    34
904     34
1881    34
313     34
879     34
1738    34
1439    34
1548    34
1684    34
1488    34
1646    34
1412    34
1801    34
2198    34
837     35
201     35
2186    35
1666    35
1281    35
1858    35
1639    35
302     35
113     35
1108    35
1114    35
1833    35
1539    35
237     35
1644    35
39      35
1165    35
2003    35
1407    35
7       35
633     35
1866    35
1356    35
659     35
18      35
486     35
353     36
2070    36
573     36
3       36
440     36
1828    36
1689    36
117     36
1753    36
276     36
1094    36
2135    36
2008    36
2012    36
1572    36
290     36
1590    36
809     36
1028    36
311     36
1953    36
1954    36
1917    36
2196    36
2040    36
702     36
380     36
1679    36
525     36
1298    36
1220    36
171     36
1854    36
1859    36
1841    36
192     36
151     36
1914    36
1068    37
1875    37
2046    37
2157    37
1316    37
1591    37
1091    37
1990    37
318     37
1715    37
314     37
1260    37
922     37
1789    37
1241    37
1096    37
1945    37
257     37
567     37
1671    37
1097    37
1761    37
850     37
1495    37
2122    37
115     37
173     37
1657    37
1695    37
872     37
1287    38
1603    38
1318    38
907     38
1698    38
1995    38
1625    38
1305    38
1814    38
405     38
1307    38
393     38
1906    38
1063    38
2013    38
1920    38
517     38
1551    38
540     38
1863    38
1323    38
159     38
663     38
223     38
284     38
926     38
694     38
19      38
1242    38
1790    38
1078    38
522     39
367     39
2079    39
2178    39
1667    39
2202    39
740     39
863     39
455     39
557     39
790     39
4       39
401     39
582     39
493     39
1457    39
2016    39
823     39
1987    39
2084    39
853     39
1056    39
982     39
2136    39
266     39
263     39
136     39
972     39
1633    39
1126    39
1622    39
1891    39
1203    39
1617    39
1157    39
1158    39
654     40
1883    40
829     40
183     40
2100    40
660     40
454     40
278     40
2128    40
2090    40
1726    40
38      40
818     40
817     40
436     40
15      40
1563    40
1015    40
800     40
105     40
813     40
949     40
1969    40
206     40
644     40
1660    40
382     40
1363    40
1458    40
944     40
544     40
2173    40
1490    40
2056    40
210     40
1653    40
1740    40
1973    40
530     40
1079    41
20      41
738     41
1154    41
551     41
1735    41
1081    41
1417    41
1132    41
1729    41
1762    41
2041    41
1754    41
494     41
1103    41
658     41
1410    41
2017    41
1101    41
927     41
930     41
1390    41
1651    41
905     41
373     41
374     41
962     41
62      41
2187    41
1283    41
849     41
2189    41
990     41
1309    41
1694    41
1699    41
750     41
1999    41
2193    41
93      41
1952    41
1335    42
859     42
976     42
869     42
1112    42
735     42
581     42
768     42
966     42
1122    42
1826    42
1049    42
555     42
1586    42
1943    42
906     42
1517    42
539     42
743     42
1059    42
1468    42
1654    42
600     42
854     42
605     42
1809    42
697     42
1798    42
1006    42
2035    42
1224    42
682     42
681     42
1629    42
1313    42
1004    42
1212    42
1276    42
1994    42
992     42
723     42
1258    42
1936    42
1960    42
773     42
1682    42
848     42
1279    42
1438    42
799     42
1686    42
1099    42
288     42
338     42
345     42
146     42
212     42
2150    42
203     42
99      42
2170    42
456     42
108     42
479     42
1581    43
48      43
1385    43
928     43
1107    43
1589    43
1894    43
1691    43
460     43
49      43
1986    43
611     43
1808    43
202     43
2048    43
1320    43
1302    43
69      43
630     43
190     43
1273    43
182     43
1065    43
1013    43
819     43
1343    43
746     43
610     43
576     43
462     43
510     43
1471    43
558     43
515     43
1751    43
1737    43
1899    43
1446    43
1180    43
147     43
885     43
1489    43
1843    43
523     43
1771    43
2010    43
1979    43
1916    43
852     44
130     44
394     44
474     44
2099    44
666     44
1327    44
2089    44
1460    44
796     44
134     44
1500    44
810     44
1652    44
310     44
431     44
1345    44
176     44
991     44
931     44
1554    44
761     44
934     44
935     44
2088    44
350     44
1831    44
968     44
707     44
769     44
704     44
2006    44
168     44
437     44
2119    44
1604    44
337     44
125     44
1532    44
909     44
469     44
332     44
1459    44
72      44
1774    44
1636    44
10      44
1925    44
527     44
1136    44
2068    44
1927    44
1214    44
1693    44
2066    44
25      44
1930    44
2060    44
35      44
1238    44
42      44
2181    44
607     44
1918    44
1755    44
71      44
489     44
1285    44
298     44
296     44
1674    44
1113    44
1475    45
574     45
1853    45
447     45
236     45
1482    45
844     45
1825    45
399     45
919     45
578     45
258     45
453     45
1314    45
1229    45
222     45
135     45
1505    45
2142    45
861     45
1835    45
513     45
1574    45
1909    45
1736    45
1743    45
1508    45
1208    45
152     45
1195    45
2166    45
792     45
2007    45
1507    45
862     45
2067    45
929     45
466     45
1355    45
67      45
1368    45
2124    45
498     45
1803    45
1819    45
270     45
1237    45
695     45
608     45
1958    45
1256    45
56      45
1259    45
1650    45
2025    45
1588    45
1349    45
2139    45
726     45
41      45
943     45
354     45
2064    45
591     45
1971    45
1970    45
1862    45
1306    45
1947    45
163     45
1868    46
2132    46
1921    46
1071    46
830     46
406     46
1341    46
241     46
200     46
1480    46
834     46
1303    46
821     46
1169    46
1115    46
1904    46
1401    46
910     46
948     46
1371    46
965     46
1125    46
1434    46
269     46
385     46
888     46
2147    46
2163    46
1133    46
878     46
1137    46
271     46
336     46
1144    46
1088    46
1001    46
1036    46
391     46
238     46
1807    46
647     46
760     46
656     46
2058    46
1692    46
598     46
2081    46
2097    46
563     46
470     46
132     46
2071    46
1783    46
1621    46
1775    46
465     46
2107    46
8       46
680     47
947     47
1424    47
186     47
76      47
938     47
2030    47
946     47
1296    47
883     47
2050    47
1394    47
1972    47
327     47
463     47
1346    47
1560    47
716     47
2115    47
1000    47
998     47
932     47
1070    47
1408    47
714     47
181     47
2021    47
1360    47
1366    47
978     47
1677    47
1272    47
1228    47
127     47
595     47
2111    47
845     47
225     47
836     47
1102    47
1478    47
1499    47
1752    47
2144    47
1913    47
1760    47
532     47
1201    47
1839    47
1583    47
778     47
2164    47
1092    47
1683    47
1678    47
870     47
616     47
1632    48
1367    48
464     48
1369    48
1288    48
1194    48
1372    48
2148    48
1192    48
461     48
215     48
1084    48
1073    48
1178    48
971     48
1940    48
2072    48
2118    48
321     48
84      48
1252    48
2153    48
1895    48
88      48
1233    48
2195    48
1266    48
577     48
70      48
1493    48
1733    48
1145    48
2156    48
1365    48
1268    48
816     48
1393    48
789     48
1402    48
788     48
1993    48
860     48
1404    48
389     48
1832    48
791     48
875     48
1425    48
438     48
459     48
893     48
1432    48
764     48
763     48
1846    48
753     48
357     48
1464    48
429     48
1481    48
730     48
1395    48
736     48
1396    48
801     48
141     48
1215    49
421     49
1483    49
435     49
621     49
6       49
1269    49
60      49
1061    49
627     49
2057    49
1164    49
1829    49
304     49
2108    49
1662    49
1496    49
887     49
535     49
1261    49
1837    49
545     49
1731    49
568     49
1225    49
1210    49
1513    49
1842    49
786     49
1465    49
1795    49
2113    49
1713    49
856     49
603     49
390     49
219     49
2145    49
1095    49
279     49
1255    49
402     49
1655    49
2087    49
1670    49
1880    49
1573    49
1357    49
1010    49
1431    49
379     49
1421    49
2158    49
452     49
1596    49
1601    49
368     49
994     49
916     49
918     49
1965    49
1018    49
1011    49
1877    49
2018    49
1861    49
759     49
933     49
480     49
255     50
2197    50
30      50
1974    50
728     50
174     50
795     50
1235    50
1170    50
450     50
417     50
34      50
2191    50
1494    50
698     50
2015    50
254     50
355     50
2019    50
2022    50
253     50
552     50
248     50
556     50
560     50
1379    50
165     50
825     50
107     50
1901    50
359     50
2075    50
1400    50
1033    50
686     50
1066    50
1265    50
1648    50
1433    50
1980    50
1810    50
1885    50
1445    50
209     50
671     50
1064    50
881     50
80      50
1444    50
628     50
629     50
64      50
2047    50
1083    50
1976    50
1452    50
1461    50
917     50
1247    50
2138    50
653     50
330     50
85      50
780     50
865     50
160     50
1282    50
122     51
235     51
2168    51
75      51
140     51
1659    51
1387    51
1193    51
1310    51
1857    51
1615    51
98      51
1613    51
1606    51
1718    51
1353    51
110     51
1722    51
1855    51
24      51
1448    51
1398    51
1267    51
1786    51
1177    51
1472    51
1374    51
208     51
1239    51
524     51
579     51
902     51
580     51
363     51
362     51
942     51
514     51
1149    51
597     51
593     51
348     51
967     51
344     51
340     51
2083    51
2059    51
884     51
997     51
841     51
1171    51
840     51
471     51
719     51
1949    51
733     51
448     51
669     51
1174    51
1951    52
1889    52
320     52
559     52
1058    52
1730    52
1301    52
188     52
1878    52
199     52
1797    52
554     52
951     52
1856    52
1867    52
1635    52
2172    52
767     52
779     52
1840    52
649     52
412     52
2109    52
1661    52
54      52
377     52
372     52
369     52
44      52
988     52
993     52
1254    52
1816    52
1756    52
247     52
1227    52
1116    52
1146    52
1922    52
1907    52
531     52
1100    52
226     52
1147    52
1991    53
665     53
2143    53
662     53
1514    53
812     53
814     53
415     53
1530    53
1111    53
1748    53
1844    53
61      53
1640    53
1005    53
882     53
1428    53
1221    53
520     53
347     53
5       53
1409    53
1975    53
1380    53
940     53
1759    53
519     53
565     53
162     53
1887    53
109     53
124     53
2200    53
83      53
112     53
1569    53
240     53
1623    53
587     54
846     54
640     54
1983    54
274     54
1253    54
1447    54
1003    54
52      54
292     54
890     54
1707    54
1687    54
153     54
251     54
335     54
1822    54
1977    54
1938    54
1834    54
1031    54
1780    54
1944    54
439     54
833     54
1284    54
1637    54
2106    54
1106    54
299     54
1029    54
1051    54
561     54
1558    54
138     54
419     54
1026    54
1277    54
2       55
1166    55
1818    55
700     55
703     55
1903    55
158     55
1998    55
1595    55
2029    55
777     55
936     55
1526    55
1487    55
1575    55
1196    55
116     55
388     55
1562    55
2096    55
752     55
2102    55
756     55
384     55
1681    55
1429    55
1893    55
128     55
1189    55
73      55
871     55
1426    55
691     55
329     55
1074    55
1060    55
322     55
221     55
1286    55
1295    55
306     55
1047    55
1934    55
503     55
2126    55
1025    55
575     55
191     55
1800    55
1089    55
1230    55
2137    55
1142    55
1140    55
1701    55
592     55
285     55
961     55
47      56
443     56
1009    56
231     56
123     56
1981    56
1734    56
1257    56
1541    56
1616    56
1519    56
2127    56
468     56
430     56
243     56
651     56
416     56
511     56
625     56
476     56
737     56
97      56
1704    56
724     56
1131    56
1928    56
529     56
495     56
294     56
1845    56
1772    56
1714    56
2123    56
1785    57
1627    57
1941    57
657     57
1950    57
1820    57
1580    57
2176    57
1246    57
261     57
194     57
1522    57
547     57
1602    57
1251    57
1599    57
1888    57
103     57
2175    57
260     57
1711    57
1135    57
892     57
641     57
1199    57
1440    57
2190    57
533     57
1337    57
1197    57
392     57
828     57
989     57
1964    57
775     58
1294    58
549     58
1806    58
1491    58
868     58
1319    58
211     58
1105    58
619     58
617     58
1935    58
1123    58
1222    58
2194    58
397     58
2086    58
516     58
941     58
807     58
652     58
351     58
1311    58
1697    58
478     58
131     58
1531    58
106     58
1794    58
2116    58
1304    58
1334    58
955     58
1766    58
921     58
218     58
1579    59
499     59
2077    59
678     59
602     59
1179    59
675     59
361     59
1626    59
1827    59
886     59
242     59
1793    59
802     59
413     59
484     59
1724    59
1045    59
307     59
1119    59
291     59
1162    59
570     59
1138    59
774     59
583     59
1533    59
1454    59
1055    59
609     60
615     60
512     60
1769    60
91      60
1620    60
2051    60
670     60
679     60
79      60
2049    60
601     60
87      60
1172    60
1289    60
1968    60
1354    60
1504    60
1352    60
1350    60
349     60
319     60
386     60
1027    60
2152    60
1299    60
1550    60
824     60
1884    60
960     60
1085    60
1243    60
100     60
467     60
696     60
259     60
1134    60
1578    60
896     60
1155    60
2114    60
496     61
953     61
1436    61
945     61
1685    61
161     61
155     61
1850    61
1607    61
1325    61
166     61
1712    61
1020    61
572     61
1882    61
11      61
1898    61
1757    61
1205    61
1912    61
1181    61
956     61
2055    61
1470    61
1641    61
805     61
1473    61
428     61
2020    61
851     61
1982    61
2026    61
867     61
66      61
95      61
1598    61
126     61
1805    61
492     61
1512    61
624     61
92      61
739     61
757     62
1054    62
509     62
121     62
445     62
1634    62
1300    62
1449    62
1069    62
1076    62
286     62
731     62
1041    62
473     62
224     62
227     62
230     62
1204    62
1163    62
699     62
1182    62
1067    62
1249    62
784     62
672     62
1403    62
631     62
145     62
613     62
63      62
1802    62
1984    62
808     62
1502    62
1420    62
1967    62
1708    62
880     62
1506    62
1988    62
877     62
1348    62
1344    62
1008    62
1016    62
149     62
2117    62
1851    62
2092    63
2160    63
1817    63
2112    63
1811    63
2155    63
1860    63
2110    63
2129    63
2151    63
2101    63
1902    63
2161    63
0       63
1672    63
333     63
1544    63
343     63
1523    63
1262    63
245     63
1202    63
787     63
1190    63
1188    63
939     63
309     63
771     63
1184    63
1422    63
832     63
81      63
1378    63
1153    63
46      63
1161    63
754     63
562     64
1555    64
1370    64
749     64
827     64
1896    64
383     64
1527    64
645     64
1329    64
1270    64
590     64
781     64
458     64
2065    64
2091    64
1996    64
1931    64
2043    64
815     64
858     64
1359    64
2203    64
1062    64
1782    64
1739    64
1048    64
980     64
1963    64
1792    64
979     64
119     64
969     64
1690    64
316     64
1185    64
1910    64
1680    64
197     64
1576    64
876     64
1594    64
300     64
1216    64
287     64
2154    64
721     64
262     64
273     64
758     65
1770    65
2005    65
1052    65
1206    65
793     65
1292    65
1191    65
745     65
1236    65
571     65
1812    65
1656    65
2177    65
1358    65
2141    65
1610    65
1577    65
1566    65
2125    65
339     65
387     65
148     65
51      65
1732    65
395     65
433     65
706     65
2027    65
1479    65
585     65
569     65
2078    65
636     65
475     65
449     65
1463    65
1706    65
45      66
984     66
1       66
2182    66
65      66
985     66
2174    66
974     66
2165    66
970     66
1090    66
729     66
184     66
185     66
196     66
899     66
198     66
205     66
898     66
365     66
806     66
797     66
2105    66
2082    66
776     66
701     66
959     66
1104    66
2204    66
1542    66
1538    66
1871    66
1631    66
1630    66
1128    66
1709    66
1813    66
1611    66
1275    66
233     67
1441    67
2001    67
154     67
432     67
711     67
1518    67
720     67
755     67
1377    67
866     67
855     67
308     67
408     67
256     67
1815    67
1382    67
2080    67
2028    67
506     67
1384    67
1053    67
1019    67
637     67
488     67
986     67
118     67
693     67
139     67
1002    67
1427    67
1109    68
281     68
1317    68
673     68
1600    68
538     68
328     68
1561    68
2039    68
1848    68
1540    68
2085    68
717     68
472     68
521     68
441     68
618     68
1997    68
68      68
1747    68
1719    68
120     68
1156    68
143     68
1768    68
1167    68
272     68
2162    68
1173    68
958     68
937     68
920     68
57      68
1669    68
187     68
1415    68
250     68
214     68
1086    68
1231    68
1244    68
12      68
1219    68
1658    68
31      68
1937    68
1038    68
550     69
566     69
33      69
1778    69
451     69
1791    69
1703    69
1673    69
1525    69
1664    69
1830    69
1645    69
303     69
220     69
2140    69
58      69
1110    69
1852    69
1776    69
2011    69
782     69
1992    69
1264    69
2024    69
1263    69
1908    69
912     69
2037    69
1919    69
1139    69
687     69
1956    69
995     69
751     69
1037    69
1926    69
1383    70
9       70
1557    70
312     70
722     70
1342    70
2009    70
620     70
772     70
1929    70
2063    70
1466    70
1443    70
483     70
1435    70
2179    70
548     70
964     70
1915    70
1543    70
2032    70
1160    70
635     70
1723    71
1040    71
144     71
1727    71
17      71
1911    71
21      71
1942    71
1032    71
1321    71
275     71
604     71
2130    71
710     71
677     71
2042    71
420     71
444     71
2076    71
674     71
537     71
1416    71
1869    71
371     71
715     71
1418    72
59      72
623     72
586     72
2038    72
1148    72
688     72
1847    72
1361    72
903     72
1392    72
204     72
164     72
424     72
1248    72
713     72
1312    72
1552    73
1720    73
1717    73
293     73
626     73
1628    73
1939    73
1966    73
1556    73
2159    73
2023    73
1905    73
1223    73
2004    73
32      74
497     74
425     74
1278    74
1419    74
1336    74
770     75
1872    75
1124    75
94      75
1308    75
1612    75
150     75
1716    75
502     76
482     76
477     76
783     76
594     76
1388    76
1250    76
1130    77
398     77
341     77
1897    77
407     79
1924    80
Name: Age, dtype: int64


age_groups = [(23,30), (31,40), (41,50), (51,60), (61,70), (71, 85)]
def assign_age_group(Age):
    for age_range in age_groups:
        if age_range[0] <= Age <= age_range[1]:
            return f"{age_range[0]} - {age_range[1]}"
    return("Unknown")
food['Age_Group'] = food['Age'].apply(assign_age_group)


food[['Age', 'Age_Group']].head()


import seaborn as sns


age_order = ['23 - 30', '31 - 40', '41 - 50', '51 - 60', '61 - 70', '71 - 85']
sns.pointplot(data = food, x='Age_Group', y = 'Accepted_Campaigns', order = age_order)

<AxesSubplot:xlabel='Age_Group', ylabel='Accepted_Campaigns'>


counts = food['Age_Group'].value_counts()


percentage = counts / food.shape[0]


percent_food = percentage.reset_index()


percent_food.columns = ['age_group', 'percentage']


percent_food = percent_food.sort_values('age_group')


percent_food


import matplotlib.pyplot as plt
sns.barplot(x = 'age_group', y = 'percentage', data = percent_food)
plt.title('Percentage of Accepted Campaigns per Age Group')
plt.show()


# Age Segmentation - core audience for accepting campaigns eight now is 31 - 70


food.groupby('Age_Group')['MntTotal'].sum().reset_index()


grouped_food = food.groupby('Age_Group')['MntTotal'].sum().reset_index()

sns.barplot(x = 'Age_Group', y = 'MntTotal', data = grouped_food)
plt.title('Amount Spent Per Age Group')
plt.show()


acct_camp = food[food['Accepted_Campaigns'] != 0]

grouped_food = acct_camp.groupby('Age_Group')['MntTotal'].sum().reset_index()

sns.barplot(x = 'Age_Group', y = 'MntTotal', data = grouped_food)
plt.title('Amount Spent Per Age Group')
plt.show()


# Age Segmentation - core audience for accepting campaigns right now 31 - 70, 23 - 30, 71 and up at higher rates.


food.head()


sum_food = pd.DataFrame(food[['NumWebPurchases', 'NumCatalogPurchases', 'NumStorePurchases']].sum(), columns = ['Sum'])


sum_food = sum_food.reset_index()


sum_food.rename(columns = {'index' : 'Type_of_Purchase'}, inplace = True)


sum_food


sns.barplot(x = 'Type_of_Purchase', y = 'Sum', data = sum_food)

<AxesSubplot:xlabel='Type_of_Purchase', ylabel='Sum'>


acct_camp = food[food['Accepted_Campaigns'] != 0]

sum_food = pd.DataFrame(acct_camp[['NumWebPurchases', 'NumCatalogPurchases', 'NumStorePurchases']].sum(), columns = ['Sum'])
sum_food = sum_food.reset_index()
sum_food.rename(columns = {'index' : 'Type_of_Purchase'}, inplace = True)
sns.barplot(x = 'Type_of_Purchase', y = 'Sum', data = sum_food)

<AxesSubplot:xlabel='Type_of_Purchase', ylabel='Sum'>


x = sns.jointplot(data = food, x = 'MntTotal', y = 'NumWebPurchases', kind = 'kde')
x.plot_joint(sns.regplot, color = 'r')

<seaborn.axisgrid.JointGrid at 0x1fa6e97fc40>


x = sns.jointplot(data = food, x = 'MntTotal', y = 'NumCatalogPurchases', kind = 'kde')
x.plot_joint(sns.regplot, color = 'r')

<seaborn.axisgrid.JointGrid at 0x1fa6ecc4ee0>


x = sns.jointplot(data = food, x = 'MntTotal', y = 'NumStorePurchases', kind = 'kde')
x.plot_joint(sns.regplot, color = 'r')

<seaborn.axisgrid.JointGrid at 0x1fa6e71dd00>


# 2 directions: Boost up the higher percentage catalog customers. OR Focus on In Store/Web because they have more traffic


sns.regplot(x = 'Total_Children', y = 'Accepted_Campaigns', data = food)

<AxesSubplot:xlabel='Total_Children', ylabel='Accepted_Campaigns'>


# Less kids = More likely to accept campagin


sns.regplot(x = 'Education_Status', y = 'Accepted_Campaigns', data = food)

<AxesSubplot:xlabel='Education_Status', ylabel='Accepted_Campaigns'>


sns.regplot(x = 'Education_Status', y = 'MntTotal', data = food)

<AxesSubplot:xlabel='Education_Status', ylabel='MntTotal'>


# Education isn't really significant in our segmentation


sns.countplot(x = 'Marital_Status_str', data = food)

<AxesSubplot:xlabel='Marital_Status_str', ylabel='count'>


sns.regplot(x = 'Marital_Status', y = 'Accepted_Campaigns', data = food)

<AxesSubplot:xlabel='Marital_Status', ylabel='Accepted_Campaigns'>


accpt = food[food['Accepted_Campaigns'] != 0]
rel_food = accpt.groupby('Marital_Status_str')['MntTotal'].sum().reset_index()


sns.barplot(x = 'Marital_Status_str', y = 'MntTotal', data = rel_food)

<AxesSubplot:xlabel='Marital_Status_str', ylabel='MntTotal'>


sns.barplot(x = 'Marital_Status_str', y = 'MntTotal', data = rel_food)

<AxesSubplot:xlabel='Marital_Status_str', ylabel='MntTotal'>


total = food['Marital_Status_str'].value_counts()
accepted = food[food['Accepted_Campaigns'] == 1]['Marital_Status_str'].value_counts()


pect_marital = accepted / total * 100


pect_food = pect_marital.reset_index()
pect_food.columns = ['Marital_Status', 'Percentage']


sns.barplot(x = 'Marital_Status', y = 'Percentage', data = pect_food)

<AxesSubplot:xlabel='Marital_Status', ylabel='Percentage'>


# Marriage - Married, Single, Together are spending a lot more money than widow and divoreced. We should focus on this segment

U Food Marketing Analysis¶

Data cleaning¶

OVERALL FINDINGS¶

1. Age - 30 -70 Were spending more money, but less likely to accept campaigns. Higher volume here though¶

Money Making¶

New Users to Spend Money¶

	Income	Kidhome	Teenhome	Recency	MntWines	MntFruits	MntMeatProducts	MntFishProducts	MntSweetProducts	MntGoldProds	...	marital_Together	education_Graduation	education_PhD	MntTotal	MntRegularProds
0	58138.0	0	0	58	635	88	546	172	88	88	...	0	1	0	1529	1441
1	46344.0	1	1	38	11	1	6	2	1	6	...	0	1	0	21	15
2	71613.0	0	0	26	426	49	127	111	21	42	...	1	1	0	734	692
3	26646.0	1	0	26	11	4	20	10	3	5	...	1	1	0	48	43
4	58293.0	1	0	94	173	43	118	46	27	15	...	0	0	1	407	392

	Income	Kidhome	Teenhome	Recency	MntWines	MntFruits	MntMeatProducts	MntFishProducts	MntSweetProducts	MntGoldProds	NumDealsPurchases	NumWebPurchases	NumCatalogPurchases	NumStorePurchases	NumWebVisitsMonth	Z_CostContact	Z_Revenue	Response	Age	Customer_Days	marital_Married	marital_Single	marital_Together	education_Graduation	education_PhD	MntTotal	MntRegularProds	Total_Children
0	58138.0	0	0	58	635	88	546	172	88	88	3	8	10	4	7	3	11	1	63	2822	0	1	0	1	0	1529	1441	0
1	46344.0	1	1	38	11	1	6	2	1	6	2	1	1	2	5	3	11	0	66	2272	0	1	0	1	0	21	15	2
2	71613.0	0	0	26	426	49	127	111	21	42	1	8	2	10	4	3	11	0	55	2471	0	0	1	1	0	734	692	0
3	26646.0	1	0	26	11	4	20	10	3	5	2	2	0	4	6	3	11	0	36	2298	0	0	1	1	0	48	43	1
4	58293.0	1	0	94	173	43	118	46	27	15	5	5	3	6	5	3	11	0	39	2320	1	0	0	0	1	407	392	1

	Income	Kidhome	Teenhome	Recency	MntWines	MntFruits	MntMeatProducts	MntFishProducts	MntSweetProducts	MntGoldProds	NumDealsPurchases	NumWebPurchases	NumCatalogPurchases	NumStorePurchases	NumWebVisitsMonth	AcceptedCmp3	AcceptedCmp1	Z_CostContact	Z_Revenue	Response	Age	Customer_Days	marital_Divorced	education_Graduation	education_Master	education_PhD	MntTotal	MntRegularProds	AcceptedCmpOverall	Total_Children
6	55635.0	0	1	34	235	65	164	50	49	27	4	7	3	7	6	0	0	3	11	0	49	2752	5	1	0	0	563	536	0	1
11	63033.0	0	0	82	194	61	480	225	112	30	1	3	4	8	2	0	0	3	11	0	61	2385	5	1	0	0	1072	1042	0	0
12	59354.0	1	1	53	233	2	53	3	5	14	3	6	1	5	6	0	0	3	11	0	68	2385	5	0	1	0	296	282	0	2
31	46610.0	0	2	8	96	12	96	33	22	43	6	4	1	6	6	0	0	3	11	1	68	2767	5	0	0	1	259	216	0	2
49	82582.0	0	0	54	510	120	550	156	40	241	1	4	9	7	1	1	1	3	11	1	43	2181	5	1	0	0	1376	1135	2	0

	age_group	percentage
5	23 - 30	0.027130
3	31 - 40	0.161693
0	41 - 50	0.332067
1	51 - 60	0.221921
2	61 - 70	0.212154
4	71 - 85	0.045035

	Age_Group	MntTotal
0	23 - 30	40166
1	31 - 40	135044
2	41 - 50	297347
3	51 - 60	242313
4	61 - 70	249793
5	71 - 85	76828

	Type_of_Purchase	Sum
0	NumWebPurchases	7619
1	NumCatalogPurchases	4871
2	NumStorePurchases	10675

U Food Marketing Analysis¶

Data cleaning¶

OVERALL FINDINGS¶

1. Age - 30 -70 Were spending more money, but less likely to accept campaigns. Higher volume here though¶

2. Catalog was mor elikely to accept campaigns, but in person spend more. Recommend a split between all.¶

Money Making¶

New Users to Spend Money¶